Classification of Adulterated Particle Images in Coconut Oil Using Deep Learning Approaches

In the production of coconut oil for consumption, cleanliness and safety are the first priorities for meeting the standard in Thailand. The presence of color, sediment, or impurities is an important element that affects consumers’ or buyers’ decision to buy coconut oil. Coconut oil contains impurities that are revealed during the process of compressing the coconut pulp to extract the oil. Therefore, the oil must be filtered by centrifugation and passed through a fine filter. When the oil filtration process is finished, staff inspect the turbidity of coconut oil by examining the color with the naked eye and should detect only the color of the coconut oil. However, this method cannot detect small impurities, suspended particles that take time to settle and become sediment. Studies have shown that the turbidity of coconut oil can be measured by passing light through the oil and applying image processing techniques. This method makes it possible to detect impurities using a microscopic camera that photographs the coconut oil. This study proposes a method for detecting impurities that cause the turbidity in coconut oil using a deep learning approach called a convolutional neural network (CNN) to solve the problem of impurity identification and image analysis. In the experiments, this paper used two coconut oil impurity datasets, PiCO_V1 and PiCO_V2, containing 1000 and 6861 images, respectively. A total of 10 CNN architectures were tested on these two datasets to determine the accuracy of the best architecture. The experimental results indicated that the MobileNetV2 architecture had the best performance, with the highest training accuracy rate, 94.05%, and testing accuracy rate, 80.20%.

Investigating the Filtration Characteristics of Direct Driven Hydraulics

Direct driven hydraulics (DDH) is receiving increasing attention due to its advantages such as high energy efficiency, easy maintenance, and compactness. However, its oil contamination management has not been surveyed in detail, whereas uncontrolled oil contamination might result in extra maintenance efforts or even downtime. Therefore, this research paper analyzes the oil filtration in direct driven hydraulics through modeling and simulation to predict the filtration effects and support the filtration design. Firstly, model blocks of the filtration characteristics are built to be added to the basic DDH dynamic model. The model can hereby include the coupling effects between fluid degradation and component wear, the filtering process, and the time-varying filter performance. Secondly, the proposed model is applied to a DDH that incorporates filtration and simulated under a duty cycle for 960 hours. The DDH efficiency and control performance when considering the contaminant are revealed. Thirdly, the results are compared between different filter selections and a filtration solution is finally proposed. In conclusion, this paper illustrates the filtration effects on the efficiency, control performance, and oil contaminant level of DDH by simulation, which can hereby support the design of the DDH filtration solution. According to the simulations, the filtered DDH resulted in 96% degradation of the pump’s volumetric efficiency after 960-hour running compared to 92% when not using any filters. The extra pressure drop introduced by the filter is below 2 bar, suggesting that the introduction of a filter with 6 μm filtration level is beneficial.

Efficiency of Using a Proxy Model for Modeling of Reservoir Pressure

The presented paper is devoted to the development and testing of a computational tool for assessment of the reservoir pressure and prompt generation of the pressure maps of collectors. The tool is based on a proxy model that allows to solve the two-dimensional diffusion equation for unsteady liquid filtration using the boundary element method. To expand the applicability of the proxy model, an algorithm for automated parameter adaptation was developed. This algorithm allows to exclude knowingly unreliable data or low-quality data from modeling. This is achieved due to analyzing the correlation between the injection, production and bottom-hole pressures for the entire well stock over the history of the reservoir development. In addition, this paper describes an approach to modeling two-phase oil and gas filtration based on the use of pseudofunctions. This approach considers the influence of gas on the oil filtration process. The use of pseudofunctions allows us to linearize the diffusion equation for two-phase filtration and to solve it using the boundary element method in the same manner as for the case of oil filtration without gas. To demonstrate the results of the proxy model validation, examples of its use for generating the pore pressure maps for two real collectors are given. The average values of the reservoir pressure at the wells calculated using the proxy model are compared with the results of the corresponding well tests and with the traditional isobar maps. The analysis showed that the average deviation of the proxy model from the real reservoir pressures is less than 10%.

Influence of filter elements on the operation of tribomechanical systems

Oil filter is a part of a gasoline or diesel engine lubrication system designed to clean the engine oil. Depending on where it is installed, the oil filtration system, they are divided into three types: - through-flow filter, which passes through all the oil that the pump feeds into the engine. A pressure regulating by-pass valve is installed upstream of the filter to protect the gaskets with oil seals. If the filter element is too dirty, the valve directs oil flow past the filter, preventing oil starvation of the bearings. Keeps engine from failing due to lack of lubrication; - a partial-flow filter is mounted parallel to the main oil line and cleans only a portion of the oil that enters the engine. Gradually the whole volume of oil passes through the filter element, giving a fairly high cleaning efficiency. However, this method does not provide absolute protection of parts from chips and other abrasives; - the combination filter combines a full-flow and a partial-flow cleaning principle. It consists of two filter elements, one mounted parallel to the oil line and the other cut into it. This ensures maximum cleaning efficiency and long filter life. The filter elements are divided into two types according to their efficiency in removing fine impurities: coarse filters, which remove coarse impurities, and fine filters, which remove fine impurities. According to the design of the housing and the possibility of replacing the filter element, filters are divided into multiple (collapsible) and disposable (non-collapsible). Modern engines may use filters in the form of a cartridge, which is inserted into a special compartment. During operation, the oil is first routed to the filter and then through the oil channels to the interacting parts in the engine. This principle is used on all standard passenger cars. A settling filter (gravity filter) is a tank with a filter element and a settling tank in which impurities are deposited by gravity. The centrifugal filter operates similarly to the gravity filter, only dirt settles in it under the action of centrifugal force resulting from the rotation of the body